Implementation of embedded system for intelligent image recognition and processing

The main challenges for image recognition in an embedded system design are the uncertainty of the mobile user's location and the limitation of measurement algorithm. This paper demonstrates an implementation of an embedded system which is used for vehicle tracking and license plate recognition. The image of the plate is scanned by the camera attached to a mobile device and then encoded data is transmitted along with the location information to a server that is located in a remote place through a wireless communication network. In order to track a user's location, the image recognition is estimated with spatial and attribute information receiving priority. In this paper, we present an embedded system for intelligent interface between vehicle and users, employing spatial relative distance algorithm. Comparing the image and location information provides comparable results, and confirms that the embedded system is fairly evaluated by the intelligent image recognition technique.